Alternatives and similar repositories for FlashMLA

Users that are interested in FlashMLA are comparing it to the libraries listed below

• ROCm / rocm_bandwidth_test
  Bandwidth test for ROCm
  ☆66Updated last week
• ROCm / TransformerEngine
  ☆51Updated this week
• ROCm / roctracer
  [DEPRECATED] Moved to ROCm/rocm-systems repo
  ☆84Updated last week
• ROCm / aotriton
  Ahead of Time (AOT) Triton Math Library
  ☆79Updated this week
• FlagOpen / FlagCX
  ☆91Updated last week
• Lin-Mao / DrGPUM
  A memory profiler for NVIDIA GPUs to explore memory inefficiencies in GPU-accelerated applications.
  ☆26Updated last year
• bytedance / ByteMLPerf
  AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…
  ☆265Updated 2 months ago
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆121Updated 5 months ago
• meta-pytorch / triton-cpu
  An experimental CPU backend for Triton (https//github.com/openai/triton)
  ☆45Updated 2 months ago
• nod-ai / SHARK-ModelDev
  Unified compiler/runtime for interfacing with PyTorch Dynamo.
  ☆101Updated 2 months ago
• wmmae / wmma_extension
  An extension library of WMMA API (Tensor Core API)
  ☆106Updated last year
• BBuf / tensorrt-llm-moe
  ☆33Updated 8 months ago
• vllm-project / flash-attention
  Fast and memory-efficient exact attention
  ☆96Updated this week
• ROCm / rccl-tests
  RCCL Performance Benchmark Tests
  ☆75Updated this week
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆112Updated last year
• FlagTree / flagtree
  FlagTree is a unified compiler for multiple AI chips, which is forked from triton-lang/triton.
  ☆90Updated last week
• Infrawaves / DeepEP_ibrc_dual-ports_multiQP
  Aims to implement dual-port and multi-qp solutions in deepEP ibrc transport
  ☆64Updated 5 months ago
• Ascend / torchair
  ☆18Updated 2 weeks ago
• flexflow / flexflow-serve
  FlexFlow Serve: Low-Latency, High-Performance LLM Serving
  ☆63Updated last month
• QianyanTech / NBAssembler
  Assembler and Decompiler for NVIDIA (Maxwell Pascal Volta Turing Ampere) GPUs.
  ☆85Updated 2 years ago
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆100Updated 3 months ago
• OpenPPL / CuAssembler
  An unofficial cuda assembler, for all generations of SASS, hopefully ：）
  ☆83Updated 2 years ago
• NVIDIA / nvshmem
  NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…
  ☆351Updated last week
• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆112Updated 5 months ago
• microsoft / ark
  A GPU-driven system framework for scalable AI applications
  ☆119Updated 8 months ago
• ROCm / triton
  Development repository for the Triton language and compiler
  ☆137Updated this week
• ROCm / AMDMIGraphX
  AMD's graph optimization engine.
  ☆258Updated this week
• NVIDIA / ib-traffic-monitor
  A TUI-based utility for real-time monitoring of InfiniBand traffic and performance metrics on the local node
  ☆30Updated last month
• roastduck / FreeTensor
  A language and compiler for irregular tensor programs.
  ☆149Updated 10 months ago
• reger-men / HPL_GPU
  High-Performance Linpack Benchmark adopted version for GPU backend
  ☆11Updated 3 years ago